© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87735
    Prev
    Next
    INDEX
    Explanations

    alphabet or letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     slu
    -0.10
     nep
    -0.10
     emulation
    -0.10
     brid
    -0.09
     concess
    -0.09
     contradict
    -0.09
     Schwe
    -0.09
     arbitration
    -0.09
     Tomas
    -0.09
     cann
    -0.09
    POSITIVE LOGITS
     alphabet
    0.46
     letter
    0.46
     letters
    0.45
     Alphabet
    0.42
     Letter
    0.40
     alph
    0.38
     alphabetical
    0.38
     Letters
    0.38
    letter
    0.37
    Letter
    0.37
    Activations Density 0.795%

    No Known Activations